Related papers: Adaptive Anchor Label Propagation for Transductive…
One of the central problems in machine learning is domain adaptation. Unlike past theoretical work, we consider a new model for subpopulation shift in the input or representation space. In this work, we propose a provably effective…
Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the…
Recent advances in semi-supervised learning methods rely on estimating the categories of unlabeled data using a model trained on the labeled data (pseudo-labeling) and using the unlabeled data for various consistency-based regularization.…
Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…
Few-shot learning often involves metric learning-based classifiers, which predict the image label by comparing the distance between the extracted feature vector and class representations. However, applying global pooling in the backend of…
We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches resort to the meta-learning paradigm, where the model…
As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance. However, existing solutions heavily rely on the exploitation of lexical features and their distributional…
Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the problem of cross-domain few-shot learning where there is a large…
Few-shot classification is a challenge in machine learning where the goal is to train a classifier using a very limited number of labeled examples. This scenario is likely to occur frequently in real life, for example when data acquisition…
Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a…
Few-shot learning remains a challenging problem, with unsatisfactory 1-shot accuracies for most real-world data. Here, we present a different perspective for data distributions in the feature space of a deep network and show how to exploit…
Few-shot classification requires adapting knowledge learned from a large annotated base dataset to recognize novel unseen classes, each represented by few labeled examples. In such a scenario, pretraining a network with high capacity on the…
One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet…
Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance.…
Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address. This work targets the problem of multi-label meta-learning, where a model learns to predict multiple labels within…
Most approaches in few-shot learning rely on costly annotated data related to the goal task domain during (pre-)training. Recently, unsupervised meta-learning methods have exchanged the annotation requirement for a reduction in few-shot…
Few-shot learning is challenging due to its very limited data and labels. Recent studies in big transfer (BiT) show that few-shot learning can greatly benefit from pretraining on large scale labeled dataset in a different domain. This paper…
Few-shot classification aims to learn a model that can generalize well to new tasks when only a few labeled samples are available. To make use of unlabeled data that are more abundantly available in real applications, Ren et al.…
In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for…